Last refreshed 2026-10-17. Next refresh: weekly.
Why use MiniMax M2.5 on NVIDIA NIM?
NVIDIA NIM offers MiniMax M2.5. NVIDIA NIM is NVIDIA's deployment platform for GPU-accelerated inference microservices.
Compare MiniMax M2.5 across 6 providers to find the best fit for your use caseInput / 1M
-
Output / 1M
-
Cache
Not sourced
Batch
Not sourced
Setup recipe
Docs fallbackInstall
Use the provider REST API or SDKAuth
Create a provider API keyCall
model: minimaxai/minimax-m2.5Model ID
minimaxai/minimax-m2.5Request example
Curated snippets for this provider are not sourced yet. Use NVIDIA NIM documentation with model ID
minimaxai/minimax-m2.5.Gotchas
- Use provider model ID "minimaxai/minimax-m2.5", not the LLMReference slug "minimax-m2.5".
Compare MiniMax M2.5 Across Providers
| Provider | Input (per 1M) | Output (per 1M) |
|---|---|---|
| NVIDIA NIM | — | — |
| Together AI | $0.30 | $1.20 |
| OpenRouter | $0.30 | $1.20 |
| Vercel AI Gateway | $0.30 | $1.20 |
| Novita AI | $0.30 | $1.20 |
Capabilities
Structured Outputs
About MiniMax M2.5
MiniMax: MiniMax M2.5 (free) available via OpenRouter. Pricing: $null/1M input, $null/1M output.
Model Specs
Released2025-03-01
Parameters230B (10B active)
Context197K
ArchitectureDecoder Only